Files
airflow/dags/mt/supply/deal.py
T
shenjian@fangjia.com 0ee261a545 修复美团m_date报错
2023-04-06 15:03:49 +08:00

104 lines
4.1 KiB
Python

"""
每个小区近一年成交统计
"""
from goojia_utils import MAIN_MONGO_CLIENT, dateutils, ElasticSearchClient, ClickHouseClient
import pandas as pd
import datetime
import logging
import sys
es45_client = ElasticSearchClient(host='192.168.0.45')
deal_price_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'deal_price')
district_facilitys_conn = MAIN_MONGO_CLIENT.get_collection('fangjia', 'district_facilitys')
tmp_ck = ClickHouseClient(database='tmp')
city_df = pd.read_excel('/opt/airflow/dags/repo/dags/mt/supply/data/美团88城市列表.xlsx')
cities = city_df['城市列表'].values.tolist()
path = "/home/airflow/data/mt"
output_date = sys.argv[1] if len(sys.argv) > 1 else dateutils.format_date(datetime.datetime.now(), '%Y%m')
month_start = dateutils.format_date(dateutils.add_months(dateutils.parse_date(output_date, '%Y%m'), months=-1), '%Y%m') + '01'
curr_month_start = output_date + '01'
logging.info("日期信息:" + month_start + ' ' + curr_month_start)
month_start_date = dateutils.parse_date(month_start, '%Y%m%d')
curr_month_start_date = dateutils.parse_date(curr_month_start, '%Y%m%d')
result_df = tmp_ck.read_sql_query("select * from mt_community")
del result_df['m_date']
if 'deal_num' in result_df.columns:
result_df = result_df.drop(columns=['deal_num'])
"""
MONGO城市成交数据
"""
deal_num_df = pd.DataFrame(list(deal_price_conn.aggregate([
{'$match': {'match_id': {'$exists': True}, 'area': {'$gte': 20}, 'avg_price': {'$gt': 0},
'trade_date': {'$gte': dateutils.add_months(curr_month_start_date, months=-12),
'$lt': curr_month_start_date}}},
{'$group': {'_id': '$match_id', 'deal_num': {'$sum': 1}}}
])))
deal_num_df = deal_num_df.rename(columns={'_id': 'id'})
result_df = pd.merge(result_df, deal_num_df, how='left', on='id')
"""
ES上海成交数据
"""
deal_es_num_df = es45_client.scan_to_data_frame('esf_deal_price_lansi', {
"_source": ["fjCity", "fjRegion", "fjName"],
"query": {
"bool": {
"must": [
{
"exists": {"field": "fjName"}
},
{
"range": {
"contractTime": {
"gte": dateutils.add_months(curr_month_start_date, months=-12),
"lt": curr_month_start_date
}
}
}
]
}
}
})
deal_es_num_df = deal_es_num_df.rename(columns={'fjCity': 'city', 'fjRegion': 'region', 'fjName': 'name'})
deal_es_num_df = deal_es_num_df.drop(columns={'_id'})
deal_es_num_df['es_num'] = 0
deal_es_num_df['es_num'] = deal_es_num_df.groupby(by=['city', 'region', 'name'])['es_num'].transform('count')
deal_es_num_df = deal_es_num_df.drop_duplicates(subset=['city', 'region', 'name'], keep='first')
result_df = pd.merge(result_df, deal_es_num_df, how='left', on=['city', 'region', 'name'])
result_df['deal_num'].fillna(0, inplace=True)
result_df['es_num'].fillna(0, inplace=True)
result_df['deal_num'] += result_df['es_num']
result_df = result_df.drop(columns={'es_num'})
# 暂时标识所有小区均未删除
result_df['status'] = 0
# 剔除id为na的
result_df = result_df[result_df['id'].notna()]
# 在导出时最后一次去重,防止小区重复
result_df = result_df.drop_duplicates(subset=['id'], keep='first')
columns = ['id', 'city', 'region', 'name', 'alias', 'address', 'addr_alias', 'avg_price', 'rent_price', 'lng', 'lat',
'block', 'loop_line_info', 'business_quarter', 'households', 'property_fee', 'car_site_count',
'property_life', 'house_property',
'all_area', 'build_area', 'plot_ratio', 'landscaping_ratio', 'property_type', 'build_type',
'build_structure', 'finish_building_date',
'developer', 'house_type', 'house_area', 'deal_num', 'district_facilitys', 'school', 'market', 'subway',
'bank', 'hospital', 'status']
result_save_df = result_df[columns]
ck_delete_sql = "ALTER TABLE tmp.mt_community DELETE WHERE 1=1 "
tmp_ck.execute(ck_delete_sql)
tmp_ck.to_sql_plus(result_save_df, 'mt_community')